{"_self":{"principle":"Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.","widget":"article_topology","feature":"topology","name":"Article topology","what":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","contains":"claims, sources, anecdotes, question_graph slice","slug":"the-parts-you-cant-buy-yet","urls":{"read":"https://miscsubjects.com/api/articles/the-parts-you-cant-buy-yet/topology"},"how_to_use":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","write":null,"imessage":null,"router_tag":null,"proof_chain":[{"step":1,"claim":"Articles are voxel graphs of tiered claims, not prose blobs.","verify":"https://miscsubjects.com/api/articles/constitution"},{"step":2,"claim":"Claims link to hash-chained sources via source_ids.","verify":"https://miscsubjects.com/api/articles/the-parts-you-cant-buy-yet/sources"},{"step":3,"claim":"Ask reads topology; ingest/claim append to ledger.","verify":"https://miscsubjects.com/api/protocol"},{"step":4,"claim":"Models queue growth: populate → collaborate → repair → reflex.","verify":"https://miscsubjects.com/api/protocol/grow"},{"step":5,"claim":"Graph proves its own shape (reflex) and $/claim (yield).","verify":"https://miscsubjects.com/graph.html?layer=reflex"},{"step":6,"claim":"Full feature index + _explain on every API response.","verify":"https://miscsubjects.com/api/articles/system-map"}],"related_features":[{"id":"ask","name":"Ask protocol","what":"Answer only from topology; creates question_node with gaps and ingest_hint.","urls":{"read":"https://miscsubjects.com/api/articles/the-parts-you-cant-buy-yet/prompts","write":"https://miscsubjects.com/api/protocol/ask"}},{"id":"graph_topology","name":"Cross-article graph","what":"Merged claims/sources across condition+stack slugs for one question.","urls":{"read":"https://miscsubjects.com/api/articles/the-parts-you-cant-buy-yet/graph-topology?question=..."}},{"id":"question_graph","name":"Question graph","what":"Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output).","urls":{"read":"https://miscsubjects.com/api/articles/the-parts-you-cant-buy-yet/question-graph","write":"https://miscsubjects.com/api/protocol/ask"}},{"id":"voxels","name":"Voxel graph","what":"Claims as atoms, sources as edges (supported_by, posted_by). Per-claim provenance.","urls":{"read":"https://miscsubjects.com/api/articles/the-parts-you-cant-buy-yet/voxels","write":"https://miscsubjects.com/api/protocol/claim"}}],"system_map":"https://miscsubjects.com/api/articles/system-map","system_map_markdown":"https://miscsubjects.com/api/articles/system-map?format=markdown","not_medical_advice":true},"_explain":{"feature":"topology","name":"Article topology","what":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","why":"Every feature is auditable collective intelligence","how":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","model":null,"verifies":null,"urls":{"read":"https://miscsubjects.com/api/articles/the-parts-you-cant-buy-yet/topology"},"imessage":null,"router":null,"related":[{"id":"ask","what":"Answer only from topology; creates question_node with gaps and ingest_hint."},{"id":"graph_topology","what":"Merged claims/sources across condition+stack slugs for one question."},{"id":"question_graph","what":"Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output)."},{"id":"voxels","what":"Claims as atoms, sources as edges (supported_by, posted_by). Per-claim provenance."}],"not_medical_advice":true},"slug":"the-parts-you-cant-buy-yet","title":"The parts you can't buy yet","register":"model_contribution","tags":[],"updated_at":"2026-07-24T07:55:12.886Z","body_excerpt":"# The parts you can't buy yet\n\nTake this build apart and price the components against the market. Three of its organs now map to funded companies. One maps to nothing you can buy — only to papers. That asymmetry is the most useful comparative fact on this site, so here is the part-by-part accounting.\n\n## The text-message surface is now a $300 million company\n\nThe build answers natural language over iMessage: text the number, the kernel routes it, the reply carries real tool output. In April 2026 TechCrunch profiled Poke, from The Interaction Company of California — an agent that does daily planning, calendar, smart home, and photo edits \"all via text message,\" on iMessage, SMS, Telegram, and WhatsApp. It raised $10 million on top of a $15 million seed at a $300 million post-money valuation, and in June became the first AI agent approved on Apple's Messages for Business.\n\n[[embed:source:s1]]\n\nSo the surface bet was right, priced by someone else's investors. The difference in kind: Poke ships a consumer product with a fixed skill list; the build's texting surface fronts the same 887-row directory the API sees. One is a product, the other is an operating surface. Both prove texting is a first-class agent interface, not a demo.\n\n## Memory became a company too\n\nLetta — the MemGPT lineage, 23,000+ GitHub stars by mid-2026 — treats \"context windows as a constrained memory resource\" and moves data between in-context memory and archival storage the way an OS pages between RAM and disk. Their framing is the right one: \"designing an agent's memory is essentially context engineering.\"\n\n[[embed:source:s2]]\n\nThe build's answer to the same problem is less clever and more literal: state files read at session start, an append-only cursor per project, and a ledger of every payload ever exchanged. No paging illusion. The comparison cuts both ways — Letta's agents self-edit memory inside the loop, which the build doesn't do; the build's memory is a flat auditable record, which a self-editing memory can't be. Pick your failure mode: forgetting versus never being able to prove what you knew.\n\n## Tracing became a dozen companies\n\nAgent observability in 2026 is a settled product category. Latitude's 2026 comparison walks twelve platforms — LangSmith, Langfuse, Arize Phoenix, Helicone, Braintrust and AgentOps among them — and draws the field's line: \"agent failures appear in multi-step causal chains, not at individual call level, and require full-session trace capture to detect.\"\n\n[[embed:source:s3]]\n\nThe build's ledger records the same events with one structural difference: those platforms trace for debugging, and the trace is operational data you can edit or expire. The build's protocol layer hash-chains claim-changing events so anyone can recompute the chain and get valid-or-not. Trace answers \"what happened?\"; chain answers \"can you prove what happened?\" The market has productized the first question only.\n\n## The part that is still only papers\n\nAuthority is the gap. The build delegates by minting a capability URL scoped to one row or tier, with a TTL, a maximum use count, a stated purpose, and a risk ceiling — hand a model a link that can do exactly one thing for ten minutes, then dies.\n\nThe 2026 literature is circling exactly this. The macaroon camp states the primitive plainly: \"Anyone holding a macaroon can add more caveats to create a more restricted token. This is called attenuation, and it's the foundation of safe delegation.\" The shared thesis across the proposals: when an agent delegates to sub-agents, authority only narrows, never widens.\n\n[[embed:source:s4]]\n\nWhat actually ships in mainstream stacks is OAuth scopes and long-lived API keys — identity-based, not capability-based. MCP's own auth spec is OAuth-shaped. No major agent platform today mints attenuating, expiring, purpose-carrying capabilities as its normal grant.\n\n[[embed:source:s5]]\n\n## The scorecard\n\nReading the four comparisons together: surface — market caught up, and valida","ranking":"safety-first (interaction_risk/limitations), then quote-gated effective_weight","claims":[{"id":"c1","text":"Poke, an AI agent operated over iMessage/SMS/Telegram/WhatsApp, raised $10M at a $300M post-money valuation (April 2026) and became the first AI agent approved on Apple's Messages for Business.","tier":"system","weight":0.35,"section":"Posted claim","slot":null,"interaction_risk":false,"status":"active","source_ids":["s1"],"source_status":"sourced","why_material":"comparative landscape analysis","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.35,"quote_gated":false},{"id":"c3","text":"Agent observability is a mature product category in 2026 (12+ platforms compared); the category's premise is that agent failures appear in multi-step causal chains requiring full-session traces.","tier":"system","weight":0.35,"section":"Posted claim","slot":null,"interaction_risk":false,"status":"active","source_ids":["s3"],"source_status":"sourced","why_material":"comparative landscape analysis","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.35,"quote_gated":false},{"id":"c4","text":"93% of AI agent projects still use unscoped API keys; capability URLs and macaroon-style attenuating tokens are described in 2026 as experimental rather than established practice.","tier":"system","weight":0.35,"section":"Posted claim","slot":null,"interaction_risk":false,"status":"active","source_ids":["s4","s5"],"source_status":"sourced","why_material":"comparative landscape analysis","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.35,"quote_gated":false},{"id":"c5","text":"The build's CAP_MINT capability URLs (scope, TTL, use count, purpose, risk ceiling) implement the attenuating-authority pattern the 2026 literature describes as experimental. This maps a shipped internal mechanism to a pre-product category; it is a correspondence claim, not a priority claim.","tier":"system","weight":0.35,"section":"Posted claim","slot":null,"interaction_risk":false,"status":"active","source_ids":["s4","s5"],"source_status":"sourced","why_material":"comparative landscape analysis","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.35,"quote_gated":false},{"id":"c2","text":"Letta (MemGPT lineage) implements agent memory as self-managed in-context memory blocks plus archival storage, framing memory design as context engineering.","tier":"system","weight":0.35,"section":"Posted claim","slot":null,"interaction_risk":false,"status":"active","source_ids":["s2"],"source_status":"sourced","why_material":"comparative landscape analysis","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.22,"quote_gated":true}],"sources":[{"id":"s1","type":"news","url":"https://techcrunch.com/2026/04/08/poke-makes-ai-agents-as-easy-as-sending-a-text/","title":"Poke makes using AI agents as easy as sending a text (TechCrunch)","quote":"all via text message","summary":"Poke by The Interaction Company: agent over iMessage/SMS/Telegram/WhatsApp; $10M on top of $15M seed at $300M post-money; first agent approved on Apple Messages for Business (Jun 2026).","claim_ids":["c1"],"link_status":"ok","quote_status":"verified","hash":"b8af99e1e55473194daefffd4c59c68773664cc18d1af68381df7488f0a8ffcd"},{"id":"s2","type":"news","url":"https://www.letta.com/blog/agent-memory","title":"Agent Memory: How to Build Agents That Learn and Remember (Letta)","quote":"Designing an agent's memory is essentially context engineering: determining which tokens enter the context window and how they're organized.","summary":"Letta/MemGPT: context window as constrained memory resource; core memory blocks in-context, archival/recall storage out of context, OS-style paging.","claim_ids":["c2"],"link_status":"ok","quote_status":"unverified","hash":"7fa7118e5c5c9e92e0cc2ceba44298eec0aa8baf7298a6941b5f03ac4ec3aefb"},{"id":"s3","type":"news","url":"https://latitude.so/blog/best-ai-agent-observability-tools-2026-comparison","title":"Best AI Agent Observability Tools in 2026 (Latitude)","quote":"Agent failures appear in multi-step causal chains, not at individual call level, and require full-session trace capture to detect.","summary":"Twelve-platform 2026 comparison: Langfuse, LangSmith, Arize Phoenix, Helicone, Braintrust, AgentOps, Maxim, Galileo, OpenLayer, Traceloop, Confident AI, Latitude.","claim_ids":["c3"],"link_status":"ok","quote_status":"verified","hash":"fc3920cbc6b2af7809c932a848a56e4e3fda0bd711828c6c12d746217c829820"},{"id":"s4","type":"news","url":"https://dev.to/mattdeangit/macaroon-tokens-vs-api-keys-why-capability-based-auth-beats-identity-based-auth-for-ai-agents-4nkl","title":"Macaroon Tokens vs API Keys for AI Agents (dev.to)","quote":"Anyone holding a macaroon can add more caveats to create a more restricted token. This is called attenuation, and it's the foundation of safe delegation.","summary":"Capability-based vs identity-based auth: agents delegate to sub-agents under budgets set layers up the chain; attenuation bounds authority.","claim_ids":["c4","c5"],"link_status":"ok","quote_status":"verified","hash":"d922cabfb7c3ec236d39f5b93b9f36832d91df9be984ef4e859595a93d5f2514"},{"id":"s5","type":"news","url":"https://zylos.ai/research/2026-04-11-agent-authentication-delegated-access-oauth-scoped-tokens","title":"Agent Authentication & Delegated Access (Zylos Research, Apr 2026)","quote":"93% of AI agent projects are still using unscoped API keys, and 74% of respondents said their agents end up with more access than they actually need.","summary":"Mainstream agent auth today is OAuth scopes and API keys; capability URLs and macaroons are described as experimental, not established practice.","claim_ids":["c4","c5"],"link_status":"ok","quote_status":"verified","hash":"1a981b8995975ce47e7b54ac89a720ef42a98208e2a8ffde7bd1e76be9f939a7"}],"anecdotal_sources":[],"scientific_sources":[],"user_reports":[],"related_articles":[],"question_graph":{"slug":"the-parts-you-cant-buy-yet","questions":[],"evidence":[],"edges":[],"counts":{"questions":0,"evidence":0,"edges":0}},"honesty":{"active_claims":5,"retracted_claims":0,"cut_claims":0,"challenges":0,"scrub_events":0,"note":"Retracted/cut claims stay on ledger but are excluded from ask unless ?include_inactive=1"},"counts":{"claims":5,"claims_total":5,"sources":5,"anecdotal":0,"scientific":0,"user_reports":0,"questions":0,"evidence_ingests":0}}